Name
Abstract | ||
|---|---|---|
Recommender systems are used in our everyday lives to help make decision-making a fast and simple process when there are a vast space of options to choose from. It is vital that these systems work efficiently to make relevant recommendations to users and ultimately, guide them to target products quickly. Furthermore, users should find it easy to provide minimal feedback on recommendations. While many recommendation techniques are capable of delivering effective results through explicit profiling based on multiple prior recommendation sessions, they fail to present sensible suggestions in certain recommendation contexts. This work looks at an approach towards improving the performance of recommenders 'in-session', while preserving a users anonymity and, minimizing the feedback burden placed on the user. Specifically, we describe and evaluate an effective strategy that uses prior recommendation session summaries to improve the efficiency of the preference-based user-feedback approach, often used in conjunction with conversational recommenders. |
Year | Venue | Field |
|---|---|---|
2005 | ICAI '05: PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2 | Information retrieval,Computer science |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lorraine Mcginty | 1 | 687 | 48.17 |
| Denise Shanley | 2 | 0 | 0.34 |
| Barry Smyth | 3 | 5711 | 414.55 |